Piergiuseppe Mallozzi
Chalmers University of Technology, University of Gothenburg, University of California, Berkeley
Papers
5
Total Citations
41
H-Index
5
About
Piergiuseppe Mallozzi is a leading researcher at the intersection of formal methods, robotics, and artificial intelligence, with a primary focus on ensuring the safety and reliability of autonomous systems. His work addresses the critical challenge of verifying the behavior of learning-enabled agents, particularly those using Reinforcement Learning (RL). Mallozzi’s major contributions include the development of runtime monitoring frameworks that enforce safety invariants on RL agents exploring complex environments, a concept detailed in his most-cited paper (16 citations). He also pioneered CROME, a contract-based framework for formal robotic mission specification, enabling engineers to automatically construct precise, logic-based mission requirements from informal descriptions. Additionally, his MoVEMo approach provides a structured methodology for engineering reward functions in RL, bridging the gap between high-level goals and low-level agent learning. Mallozzi’s work on contract-based specification refinement and repair for mission planning further advances the field by allowing formal specifications to be dynamically adapted. With applications ranging from automotive architectures to autonomous robotics, his research has garnered over 40 citations, establishing him as a key figure in building trustworthy, verifiable autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2CROME: Contract-Based Robotic Mission Specification7 citations · 2020
- 3MoVEMo: A Structured Approach for Engineering Reward Functions7 citations · 2018
- 4A Proposal for an Automotive Architecture Framework for Volvo Cars6 citations · 2016
- 5Contract-Based Specification Refinement and Repair for Mission Planning5 citations · 2023